aienthuguy
commited on
Commit
•
db2ca29
1
Parent(s):
cc9e49b
Upload folder using huggingface_hub
Browse files- README.md +45 -0
- adapter_config.json +29 -0
- adapter_model.safetensors +3 -0
- checkpoint-380/README.md +204 -0
- checkpoint-380/adapter_config.json +29 -0
- checkpoint-380/adapter_model.safetensors +3 -0
- checkpoint-380/optimizer.pt +3 -0
- checkpoint-380/pytorch_model.bin +3 -0
- checkpoint-380/rng_state.pth +3 -0
- checkpoint-380/scheduler.pt +3 -0
- checkpoint-380/special_tokens_map.json +24 -0
- checkpoint-380/tokenizer.json +0 -0
- checkpoint-380/tokenizer.model +3 -0
- checkpoint-380/tokenizer_config.json +40 -0
- checkpoint-380/trainer_state.json +462 -0
- checkpoint-380/training_args.bin +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +40 -0
- training_args.bin +3 -0
- training_params.json +47 -0
README.md
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- autotrain
|
4 |
+
- text-generation-inference
|
5 |
+
- text-generation
|
6 |
+
- peft
|
7 |
+
library_name: transformers
|
8 |
+
widget:
|
9 |
+
- messages:
|
10 |
+
- role: user
|
11 |
+
content: What is your favorite condiment?
|
12 |
+
license: other
|
13 |
+
---
|
14 |
+
|
15 |
+
# Model Trained Using AutoTrain
|
16 |
+
|
17 |
+
This model was trained using AutoTrain. For more information, please visit [AutoTrain](https://hf.co/docs/autotrain).
|
18 |
+
|
19 |
+
# Usage
|
20 |
+
|
21 |
+
```python
|
22 |
+
|
23 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
24 |
+
|
25 |
+
model_path = "PATH_TO_THIS_REPO"
|
26 |
+
|
27 |
+
tokenizer = AutoTokenizer.from_pretrained(model_path)
|
28 |
+
model = AutoModelForCausalLM.from_pretrained(
|
29 |
+
model_path,
|
30 |
+
device_map="auto",
|
31 |
+
torch_dtype='auto'
|
32 |
+
).eval()
|
33 |
+
|
34 |
+
# Prompt content: "hi"
|
35 |
+
messages = [
|
36 |
+
{"role": "user", "content": "hi"}
|
37 |
+
]
|
38 |
+
|
39 |
+
input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
|
40 |
+
output_ids = model.generate(input_ids.to('cuda'))
|
41 |
+
response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
|
42 |
+
|
43 |
+
# Model response: "Hello! How can I assist you today?"
|
44 |
+
print(response)
|
45 |
+
```
|
adapter_config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "TinyPixel/Llama-2-7B-bf16-sharded",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 32,
|
14 |
+
"lora_dropout": 0.05,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 16,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"q_proj",
|
24 |
+
"v_proj"
|
25 |
+
],
|
26 |
+
"task_type": "CAUSAL_LM",
|
27 |
+
"use_dora": false,
|
28 |
+
"use_rslora": false
|
29 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ffd2ef1a49c60c65b059b97b620faeb9a1a30f7fa3df5c48729793a8fb4ba6c
|
3 |
+
size 33571624
|
checkpoint-380/README.md
ADDED
@@ -0,0 +1,204 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: TinyPixel/Llama-2-7B-bf16-sharded
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
|
201 |
+
|
202 |
+
### Framework versions
|
203 |
+
|
204 |
+
- PEFT 0.10.0
|
checkpoint-380/adapter_config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "TinyPixel/Llama-2-7B-bf16-sharded",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 32,
|
14 |
+
"lora_dropout": 0.05,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 16,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"q_proj",
|
24 |
+
"v_proj"
|
25 |
+
],
|
26 |
+
"task_type": "CAUSAL_LM",
|
27 |
+
"use_dora": false,
|
28 |
+
"use_rslora": false
|
29 |
+
}
|
checkpoint-380/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ffd2ef1a49c60c65b059b97b620faeb9a1a30f7fa3df5c48729793a8fb4ba6c
|
3 |
+
size 33571624
|
checkpoint-380/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c90df5e0496acec27518ddf406acd9901a815b05877b925e9d4c884b1cb766ef
|
3 |
+
size 67217018
|
checkpoint-380/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:049c26b844b79121ddd8379f7f69194e63f6fbf6aa007eeac0c66f17eebb8893
|
3 |
+
size 888
|
checkpoint-380/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f1bad18e3c801326d631ce197264e3a77e02c6de697b4b22ff889633f8be3924
|
3 |
+
size 14244
|
checkpoint-380/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4a8f04e98c3eac435a55fac4d3bb3b9598b213120a9f4f81c9602631ee3fadd8
|
3 |
+
size 1064
|
checkpoint-380/special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "</s>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": true,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
checkpoint-380/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-380/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
checkpoint-380/tokenizer_config.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": true,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
}
|
29 |
+
},
|
30 |
+
"bos_token": "<s>",
|
31 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
32 |
+
"clean_up_tokenization_spaces": false,
|
33 |
+
"eos_token": "</s>",
|
34 |
+
"model_max_length": 1200,
|
35 |
+
"pad_token": "</s>",
|
36 |
+
"sp_model_kwargs": {},
|
37 |
+
"tokenizer_class": "LlamaTokenizer",
|
38 |
+
"unk_token": "<unk>",
|
39 |
+
"use_default_system_prompt": false
|
40 |
+
}
|
checkpoint-380/trainer_state.json
ADDED
@@ -0,0 +1,462 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 20.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 380,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.32,
|
13 |
+
"grad_norm": 0.18415243923664093,
|
14 |
+
"learning_rate": 3.157894736842105e-05,
|
15 |
+
"loss": 0.9158,
|
16 |
+
"step": 6
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.63,
|
20 |
+
"grad_norm": 0.17151106894016266,
|
21 |
+
"learning_rate": 6.31578947368421e-05,
|
22 |
+
"loss": 0.8454,
|
23 |
+
"step": 12
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.95,
|
27 |
+
"grad_norm": 0.253557026386261,
|
28 |
+
"learning_rate": 9.473684210526316e-05,
|
29 |
+
"loss": 0.9068,
|
30 |
+
"step": 18
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 1.26,
|
34 |
+
"grad_norm": 0.44574955105781555,
|
35 |
+
"learning_rate": 0.0001263157894736842,
|
36 |
+
"loss": 0.781,
|
37 |
+
"step": 24
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 1.58,
|
41 |
+
"grad_norm": 0.3264688551425934,
|
42 |
+
"learning_rate": 0.00015789473684210527,
|
43 |
+
"loss": 0.6487,
|
44 |
+
"step": 30
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 1.89,
|
48 |
+
"grad_norm": 0.33505332469940186,
|
49 |
+
"learning_rate": 0.00018947368421052632,
|
50 |
+
"loss": 0.6935,
|
51 |
+
"step": 36
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 2.21,
|
55 |
+
"grad_norm": 0.3825117349624634,
|
56 |
+
"learning_rate": 0.0001976608187134503,
|
57 |
+
"loss": 0.606,
|
58 |
+
"step": 42
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 2.53,
|
62 |
+
"grad_norm": 0.31299710273742676,
|
63 |
+
"learning_rate": 0.00019415204678362573,
|
64 |
+
"loss": 0.513,
|
65 |
+
"step": 48
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 2.84,
|
69 |
+
"grad_norm": 0.5375415682792664,
|
70 |
+
"learning_rate": 0.00019064327485380117,
|
71 |
+
"loss": 0.5365,
|
72 |
+
"step": 54
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 3.16,
|
76 |
+
"grad_norm": 0.4755648374557495,
|
77 |
+
"learning_rate": 0.0001871345029239766,
|
78 |
+
"loss": 0.3908,
|
79 |
+
"step": 60
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 3.47,
|
83 |
+
"grad_norm": 0.9289490580558777,
|
84 |
+
"learning_rate": 0.00018362573099415207,
|
85 |
+
"loss": 0.3798,
|
86 |
+
"step": 66
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 3.79,
|
90 |
+
"grad_norm": 0.4700639247894287,
|
91 |
+
"learning_rate": 0.0001801169590643275,
|
92 |
+
"loss": 0.4379,
|
93 |
+
"step": 72
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 4.11,
|
97 |
+
"grad_norm": 0.5703785419464111,
|
98 |
+
"learning_rate": 0.00017660818713450294,
|
99 |
+
"loss": 0.3724,
|
100 |
+
"step": 78
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 4.42,
|
104 |
+
"grad_norm": 0.6487219333648682,
|
105 |
+
"learning_rate": 0.00017309941520467836,
|
106 |
+
"loss": 0.3439,
|
107 |
+
"step": 84
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 4.74,
|
111 |
+
"grad_norm": 0.599611759185791,
|
112 |
+
"learning_rate": 0.0001695906432748538,
|
113 |
+
"loss": 0.2867,
|
114 |
+
"step": 90
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 5.05,
|
118 |
+
"grad_norm": 0.5314879417419434,
|
119 |
+
"learning_rate": 0.00016608187134502925,
|
120 |
+
"loss": 0.3,
|
121 |
+
"step": 96
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 5.37,
|
125 |
+
"grad_norm": 1.1346584558486938,
|
126 |
+
"learning_rate": 0.0001625730994152047,
|
127 |
+
"loss": 0.2441,
|
128 |
+
"step": 102
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 5.68,
|
132 |
+
"grad_norm": 0.7600080370903015,
|
133 |
+
"learning_rate": 0.00015906432748538012,
|
134 |
+
"loss": 0.2277,
|
135 |
+
"step": 108
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 6.0,
|
139 |
+
"grad_norm": 0.8896855711936951,
|
140 |
+
"learning_rate": 0.00015555555555555556,
|
141 |
+
"loss": 0.2157,
|
142 |
+
"step": 114
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 6.32,
|
146 |
+
"grad_norm": 0.7400574684143066,
|
147 |
+
"learning_rate": 0.00015204678362573098,
|
148 |
+
"loss": 0.1671,
|
149 |
+
"step": 120
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 6.63,
|
153 |
+
"grad_norm": 0.7485764622688293,
|
154 |
+
"learning_rate": 0.00014853801169590643,
|
155 |
+
"loss": 0.2079,
|
156 |
+
"step": 126
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 6.95,
|
160 |
+
"grad_norm": 0.7054488658905029,
|
161 |
+
"learning_rate": 0.00014502923976608188,
|
162 |
+
"loss": 0.1424,
|
163 |
+
"step": 132
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 7.26,
|
167 |
+
"grad_norm": 1.1137595176696777,
|
168 |
+
"learning_rate": 0.00014152046783625732,
|
169 |
+
"loss": 0.1406,
|
170 |
+
"step": 138
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 7.58,
|
174 |
+
"grad_norm": 0.860434889793396,
|
175 |
+
"learning_rate": 0.00013801169590643274,
|
176 |
+
"loss": 0.1158,
|
177 |
+
"step": 144
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 7.89,
|
181 |
+
"grad_norm": 0.7475857138633728,
|
182 |
+
"learning_rate": 0.0001345029239766082,
|
183 |
+
"loss": 0.11,
|
184 |
+
"step": 150
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 8.21,
|
188 |
+
"grad_norm": 0.5861940979957581,
|
189 |
+
"learning_rate": 0.00013099415204678364,
|
190 |
+
"loss": 0.0968,
|
191 |
+
"step": 156
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 8.53,
|
195 |
+
"grad_norm": 0.6981809139251709,
|
196 |
+
"learning_rate": 0.00012748538011695908,
|
197 |
+
"loss": 0.104,
|
198 |
+
"step": 162
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 8.84,
|
202 |
+
"grad_norm": 0.7109177112579346,
|
203 |
+
"learning_rate": 0.0001239766081871345,
|
204 |
+
"loss": 0.0704,
|
205 |
+
"step": 168
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 9.16,
|
209 |
+
"grad_norm": 0.4005749523639679,
|
210 |
+
"learning_rate": 0.00012046783625730995,
|
211 |
+
"loss": 0.0757,
|
212 |
+
"step": 174
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 9.47,
|
216 |
+
"grad_norm": 0.719237744808197,
|
217 |
+
"learning_rate": 0.00011695906432748539,
|
218 |
+
"loss": 0.0697,
|
219 |
+
"step": 180
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 9.79,
|
223 |
+
"grad_norm": 0.9757436513900757,
|
224 |
+
"learning_rate": 0.00011345029239766083,
|
225 |
+
"loss": 0.0614,
|
226 |
+
"step": 186
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 10.11,
|
230 |
+
"grad_norm": 0.5613590478897095,
|
231 |
+
"learning_rate": 0.00010994152046783625,
|
232 |
+
"loss": 0.0496,
|
233 |
+
"step": 192
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 10.42,
|
237 |
+
"grad_norm": 0.49901968240737915,
|
238 |
+
"learning_rate": 0.00010643274853801171,
|
239 |
+
"loss": 0.0476,
|
240 |
+
"step": 198
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 10.74,
|
244 |
+
"grad_norm": 0.637506902217865,
|
245 |
+
"learning_rate": 0.00010292397660818713,
|
246 |
+
"loss": 0.0442,
|
247 |
+
"step": 204
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 11.05,
|
251 |
+
"grad_norm": 0.3163486421108246,
|
252 |
+
"learning_rate": 9.941520467836257e-05,
|
253 |
+
"loss": 0.0327,
|
254 |
+
"step": 210
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 11.37,
|
258 |
+
"grad_norm": 0.34687891602516174,
|
259 |
+
"learning_rate": 9.590643274853801e-05,
|
260 |
+
"loss": 0.0302,
|
261 |
+
"step": 216
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 11.68,
|
265 |
+
"grad_norm": 0.505370020866394,
|
266 |
+
"learning_rate": 9.239766081871345e-05,
|
267 |
+
"loss": 0.0278,
|
268 |
+
"step": 222
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 12.0,
|
272 |
+
"grad_norm": 1.4929355382919312,
|
273 |
+
"learning_rate": 8.888888888888889e-05,
|
274 |
+
"loss": 0.0429,
|
275 |
+
"step": 228
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 12.32,
|
279 |
+
"grad_norm": 0.2789619266986847,
|
280 |
+
"learning_rate": 8.538011695906433e-05,
|
281 |
+
"loss": 0.0213,
|
282 |
+
"step": 234
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 12.63,
|
286 |
+
"grad_norm": 0.41602373123168945,
|
287 |
+
"learning_rate": 8.187134502923976e-05,
|
288 |
+
"loss": 0.0188,
|
289 |
+
"step": 240
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 12.95,
|
293 |
+
"grad_norm": 0.38267752528190613,
|
294 |
+
"learning_rate": 7.836257309941521e-05,
|
295 |
+
"loss": 0.027,
|
296 |
+
"step": 246
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 13.26,
|
300 |
+
"grad_norm": 0.3227517008781433,
|
301 |
+
"learning_rate": 7.485380116959064e-05,
|
302 |
+
"loss": 0.0172,
|
303 |
+
"step": 252
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 13.58,
|
307 |
+
"grad_norm": 0.5111700892448425,
|
308 |
+
"learning_rate": 7.134502923976609e-05,
|
309 |
+
"loss": 0.0189,
|
310 |
+
"step": 258
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 13.89,
|
314 |
+
"grad_norm": 0.25930657982826233,
|
315 |
+
"learning_rate": 6.783625730994152e-05,
|
316 |
+
"loss": 0.0157,
|
317 |
+
"step": 264
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 14.21,
|
321 |
+
"grad_norm": 0.4176621437072754,
|
322 |
+
"learning_rate": 6.432748538011695e-05,
|
323 |
+
"loss": 0.0166,
|
324 |
+
"step": 270
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 14.53,
|
328 |
+
"grad_norm": 0.45017266273498535,
|
329 |
+
"learning_rate": 6.0818713450292395e-05,
|
330 |
+
"loss": 0.0148,
|
331 |
+
"step": 276
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 14.84,
|
335 |
+
"grad_norm": 0.2901971638202667,
|
336 |
+
"learning_rate": 5.7309941520467835e-05,
|
337 |
+
"loss": 0.013,
|
338 |
+
"step": 282
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 15.16,
|
342 |
+
"grad_norm": 0.1628808230161667,
|
343 |
+
"learning_rate": 5.3801169590643275e-05,
|
344 |
+
"loss": 0.0112,
|
345 |
+
"step": 288
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 15.47,
|
349 |
+
"grad_norm": 0.2727632224559784,
|
350 |
+
"learning_rate": 5.0292397660818715e-05,
|
351 |
+
"loss": 0.011,
|
352 |
+
"step": 294
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 15.79,
|
356 |
+
"grad_norm": 0.15591496229171753,
|
357 |
+
"learning_rate": 4.678362573099415e-05,
|
358 |
+
"loss": 0.0098,
|
359 |
+
"step": 300
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 16.11,
|
363 |
+
"grad_norm": 0.15791279077529907,
|
364 |
+
"learning_rate": 4.327485380116959e-05,
|
365 |
+
"loss": 0.013,
|
366 |
+
"step": 306
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 16.42,
|
370 |
+
"grad_norm": 0.07889483869075775,
|
371 |
+
"learning_rate": 3.976608187134503e-05,
|
372 |
+
"loss": 0.0116,
|
373 |
+
"step": 312
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 16.74,
|
377 |
+
"grad_norm": 0.12881968915462494,
|
378 |
+
"learning_rate": 3.625730994152047e-05,
|
379 |
+
"loss": 0.0088,
|
380 |
+
"step": 318
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 17.05,
|
384 |
+
"grad_norm": 0.1373162418603897,
|
385 |
+
"learning_rate": 3.274853801169591e-05,
|
386 |
+
"loss": 0.0078,
|
387 |
+
"step": 324
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 17.37,
|
391 |
+
"grad_norm": 0.07368919253349304,
|
392 |
+
"learning_rate": 2.9239766081871346e-05,
|
393 |
+
"loss": 0.0075,
|
394 |
+
"step": 330
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 17.68,
|
398 |
+
"grad_norm": 0.10508895665407181,
|
399 |
+
"learning_rate": 2.5730994152046783e-05,
|
400 |
+
"loss": 0.0085,
|
401 |
+
"step": 336
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 18.0,
|
405 |
+
"grad_norm": 0.10840031504631042,
|
406 |
+
"learning_rate": 2.2222222222222223e-05,
|
407 |
+
"loss": 0.0079,
|
408 |
+
"step": 342
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 18.32,
|
412 |
+
"grad_norm": 0.07944358885288239,
|
413 |
+
"learning_rate": 1.871345029239766e-05,
|
414 |
+
"loss": 0.0072,
|
415 |
+
"step": 348
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 18.63,
|
419 |
+
"grad_norm": 0.10223820805549622,
|
420 |
+
"learning_rate": 1.5204678362573099e-05,
|
421 |
+
"loss": 0.008,
|
422 |
+
"step": 354
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 18.95,
|
426 |
+
"grad_norm": 0.11620509624481201,
|
427 |
+
"learning_rate": 1.1695906432748537e-05,
|
428 |
+
"loss": 0.0078,
|
429 |
+
"step": 360
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 19.26,
|
433 |
+
"grad_norm": 0.08788104355335236,
|
434 |
+
"learning_rate": 8.187134502923977e-06,
|
435 |
+
"loss": 0.0083,
|
436 |
+
"step": 366
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 19.58,
|
440 |
+
"grad_norm": 0.1308579444885254,
|
441 |
+
"learning_rate": 4.678362573099415e-06,
|
442 |
+
"loss": 0.0071,
|
443 |
+
"step": 372
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 19.89,
|
447 |
+
"grad_norm": 0.09444822371006012,
|
448 |
+
"learning_rate": 1.1695906432748538e-06,
|
449 |
+
"loss": 0.0079,
|
450 |
+
"step": 378
|
451 |
+
}
|
452 |
+
],
|
453 |
+
"logging_steps": 6,
|
454 |
+
"max_steps": 380,
|
455 |
+
"num_input_tokens_seen": 0,
|
456 |
+
"num_train_epochs": 20,
|
457 |
+
"save_steps": 500,
|
458 |
+
"total_flos": 3.007882350034944e+16,
|
459 |
+
"train_batch_size": 2,
|
460 |
+
"trial_name": null,
|
461 |
+
"trial_params": null
|
462 |
+
}
|
checkpoint-380/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e0b35f1702a8421b57910707769e782c258b2a2e7af81e526fb83d2c78fa7cc7
|
3 |
+
size 4920
|
special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "</s>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": true,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
tokenizer_config.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": true,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
}
|
29 |
+
},
|
30 |
+
"bos_token": "<s>",
|
31 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
32 |
+
"clean_up_tokenization_spaces": false,
|
33 |
+
"eos_token": "</s>",
|
34 |
+
"model_max_length": 1200,
|
35 |
+
"pad_token": "</s>",
|
36 |
+
"sp_model_kwargs": {},
|
37 |
+
"tokenizer_class": "LlamaTokenizer",
|
38 |
+
"unk_token": "<unk>",
|
39 |
+
"use_default_system_prompt": false
|
40 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e0b35f1702a8421b57910707769e782c258b2a2e7af81e526fb83d2c78fa7cc7
|
3 |
+
size 4920
|
training_params.json
ADDED
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"model": "TinyPixel/Llama-2-7B-bf16-sharded",
|
3 |
+
"project_name": "myllm",
|
4 |
+
"data_path": "aienthuguy/casesTest",
|
5 |
+
"train_split": "test",
|
6 |
+
"valid_split": null,
|
7 |
+
"add_eos_token": true,
|
8 |
+
"block_size": -1,
|
9 |
+
"model_max_length": 1200,
|
10 |
+
"padding": null,
|
11 |
+
"trainer": "sft",
|
12 |
+
"use_flash_attention_2": false,
|
13 |
+
"log": "none",
|
14 |
+
"disable_gradient_checkpointing": false,
|
15 |
+
"logging_steps": -1,
|
16 |
+
"evaluation_strategy": "epoch",
|
17 |
+
"save_total_limit": 1,
|
18 |
+
"save_strategy": "epoch",
|
19 |
+
"auto_find_batch_size": false,
|
20 |
+
"mixed_precision": null,
|
21 |
+
"lr": 0.0002,
|
22 |
+
"epochs": 20,
|
23 |
+
"batch_size": 2,
|
24 |
+
"warmup_ratio": 0.1,
|
25 |
+
"gradient_accumulation": 1,
|
26 |
+
"optimizer": "adamw_torch",
|
27 |
+
"scheduler": "linear",
|
28 |
+
"weight_decay": 0.0,
|
29 |
+
"max_grad_norm": 1.0,
|
30 |
+
"seed": 42,
|
31 |
+
"chat_template": null,
|
32 |
+
"quantization": "int4",
|
33 |
+
"target_modules": null,
|
34 |
+
"merge_adapter": false,
|
35 |
+
"peft": true,
|
36 |
+
"lora_r": 16,
|
37 |
+
"lora_alpha": 32,
|
38 |
+
"lora_dropout": 0.05,
|
39 |
+
"model_ref": null,
|
40 |
+
"dpo_beta": 0.1,
|
41 |
+
"prompt_text_column": "prompt",
|
42 |
+
"text_column": "text",
|
43 |
+
"rejected_text_column": "rejected",
|
44 |
+
"push_to_hub": true,
|
45 |
+
"repo_id": "aienthuguy/test_case_assistant",
|
46 |
+
"username": null
|
47 |
+
}
|